quarantine 'em

What if you WANT to create a biased machine? What if, based on everything I've just said, you've realised, correctly, that a biased machine is a highly effective, highly deniable way to deliver your bias?

In Mickens' "Tragedy of Darth Tay the Bigoted" the causes and effects are incredibly stark and easy to unthread. If an attacker has control over the A.I.'s training data, of *course* the resulting A.I. will misbehave

So what happens if any of the humans listed below is an attacker? And the system they're attacking is the very important real-world system which they are all nominally working together to automate? The criminal justice system or the healthcare system?https://twitter.com/qntm/status/1030837348630708224 …

Mickens gives a high-level goal of computer security as "ensuring that systems do the right thing, even in the presence of malicious inputs". In a machine learning scenario, inputs come from a whole lot of places which are not the user

Or, of course, you can secretly replace the "A.I."/"machine decision-maker" with a highly biased human or collection of humans Yeah, you were randomly selected by this button which I press when I want the machine to randomly select you

* Machine learning is money laundering for bias * Machine learning is money laundering for responsibility * People do not launder their money by ACCIDENT * Assign responsibility to humans

Machines are going to be given control of the world so that they can more effectively and deniably implement the biases of the people who create and install them

So to sum up, generally I agree with James Mickens but I prefer to read less incompetence and more malice into the machine learning situation. I think this is a sound and necessary defensive strategy, regardless of the actual amount of malice involved